Metraipolis › archive › dc_f71d05725bad
You've Seen Enough: Quality-Constrained Image Coding for Machines — arXiv:2609.25108
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25108
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:46:03.928Z
- SHA-256 of the archived text
c20a164c5bb2b4cd9f48364398ededecb052e1fd6e6e42623ad58a9163c6eb55- Stable URL of this page
https://metraipolis.com/documento/dc_f71d05725bad
How to cite
You've Seen Enough: Quality-Constrained Image Coding for Machines — arXiv:2609.25108 — arXiv (en), https://arxiv.org/abs/2609.25108 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f71d05725bad (Metraipolis archive dc_f71d05725bad, sha256 c20a164c5bb2b4cd9f48364398ededecb052e1fd6e6e42623ad58a9163c6eb55)
BibTeX
@misc{dcf71d05725bad,
title = {You've Seen Enough: Quality-Constrained Image Coding for Machines — arXiv:2609.25108},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25108},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f71d05725bad; sha256 c20a164c5bb2b4cd9f48364398ededecb052e1fd6e6e42623ad58a9163c6eb55},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25108. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visual data is increasingly consumed by machine-vision systems rather than by human observers. Image Coding for Machines (ICM) compresses images assuming the main observer is a computer vision application and that the human observer needs to inspect or validate the decisions. Inspired by just-noticeable distortion, we cap human-observed quality at a desired level and devote the remaining bits to machine performance. Specifically, joint compression-segmentation training is recast as a constrained optimization problem in which the codec must meet a predefined acceptable target visual quality while a task term consumes the remaining coding capacity. This paper proposes two variants of a penalty function that guides the quality toward the target: an absolute function and a bilinear function, the latter applying a steeper slope once the target visual quality is exceeded. Experimental results show that, under the quality constraint, the proposed method achieves BD-rates of $-22.82\%$ and $-29.81\%$ relative to an unconstrained joint rate--distortion--task optimization and a simple rate--distortion baseline, respectively, showcasing bitrate reduction with the same task performance. This is achieved while the codec also meets the target visual quality with a reasonable error and without adding any complexity overhead. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.25108 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T13:18:38.198Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).